{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:X55HTSA7F6SCGI4XHYVE7C766Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f19fa936634074227377d02099e27e61253cadf34ff2ee07673bfaf7a4778a6b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T04:11:09Z","title_canon_sha256":"ebf0ebea3189e067818b396123e70164182aa50adf4c8eb9e3b6c3355972ab84"},"schema_version":"1.0","source":{"id":"2103.02827","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.02827","created_at":"2026-07-05T02:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2103.02827v2","created_at":"2026-07-05T02:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02827","created_at":"2026-07-05T02:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"X55HTSA7F6SC","created_at":"2026-07-05T02:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"X55HTSA7F6SCGI4X","created_at":"2026-07-05T02:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"X55HTSA7","created_at":"2026-07-05T02:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:033ba76deab48fc271c59422279ea05dbd8b46e136d176dad1758d2c2a15da4a","target":"graph","created_at":"2026-07-05T02:20:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.02827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the coherent risk is difficult in Markov decision processes, recent work tends to focus on the Markov coherent risk (MCR), a time-consistent surrogate. While, policy gradient (PG) updates have been derived for this objective, it remains unclear (i) whether PG finds a global optimum for MCR; (ii) how to estimate the gradient in a tractable manner. In this paper, we demo","authors_text":"Audrey Huang, Kamyar Azizzadenesheli, Liu Leqi, Zachary C. Lipton","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T04:11:09Z","title":"On the Convergence and Optimality of Policy Gradient for Markov Coherent Risk"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02827","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:18dd6c5fb9613b9fbc05bc4a847b8f3d5a9b5752f0f4402306451405b8531eb7","target":"record","created_at":"2026-07-05T02:20:43Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f19fa936634074227377d02099e27e61253cadf34ff2ee07673bfaf7a4778a6b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T04:11:09Z","title_canon_sha256":"ebf0ebea3189e067818b396123e70164182aa50adf4c8eb9e3b6c3355972ab84"},"schema_version":"1.0","source":{"id":"2103.02827","kind":"arxiv","version":2}},"canonical_sha256":"bf7a79c81f2fa42323973e2a4f8bfef43b917bd660a531cf248007948553b6d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf7a79c81f2fa42323973e2a4f8bfef43b917bd660a531cf248007948553b6d1","first_computed_at":"2026-07-05T02:20:43.490779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:43.490779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xt5ubUX2+jeIC0Yq0BJ72KM26Np9JV3xUOG0PWCTUl/BRfv1kjEmhAxf2heN9x9HSdPc9tN2twpu2KKoOfIECw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:43.491268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.02827","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18dd6c5fb9613b9fbc05bc4a847b8f3d5a9b5752f0f4402306451405b8531eb7","sha256:033ba76deab48fc271c59422279ea05dbd8b46e136d176dad1758d2c2a15da4a"],"state_sha256":"3440c58191d5a7f5db524eb0102176a9061e54bbd39a018185d19664d7d346f5"}